Probabilistic Graphical Model 1.4節

以下內容是我閱讀Probabilistic Graphical Model, Koller 2009一書的讀書筆記，未來將不定期新增內容，此技術屬AI人工智慧範疇。

1.4 Historical Notes

這節闡述Probabilistic Graphical Model的崛起歷史，當中尚做了一些關鍵書籍的推薦。

為什麼我會深耕Probabilistic Graphical Model呢？明明AI有很多領域，例如當今最夯的Transformer就是一例，原因是當今的AI沒辦法做到Reasoning與Causality，只能做模仿，而做不了思考，而這些正是Probabilistic Graphical Model可以做到的，我認為這才是未來人工智慧的趨勢。

The widespread acceptance of probabilistic methods began in the late 1980s, driven forward by two major factors. The first was a series of seminal theoretical developments. The most influential among these was the development of the Bayesian network framework by Judea Pearl and his colleagues in a series of paper that culminated in Pearl’s highly influential textbook Probabilistic Reasoning in Intelligent Systems (Pearl 1988). In parallel, the key paper by S.L. Lauritzen and D.J. Spiegelhalter 1988 set forth the foundations for efficient reasoning using probabilistic graphical models. The second major factor was the construction of large-scale, highly successful expert systems based on this framework that avoided the unrealistically strong assumptions made by early probabilistic expert systems. The most visible of these applications was the Pathfinder expert system, constructed by Heckerman and colleagues (Heckerman et al. 1992; Heckerman and Nathwani 1992b), which used a Bayesian network for diagnosis of pathology samples.

At this time, although work on other approaches to uncertain reasoning continues, probabilistic methods in general, and probabilistic graphical models in particular, have gained almost universal acceptance in a wide range of communities. They are in common use in fields as diverse as medical diagnosis, fault diagnosis, analysis of genetic and genomic data, communication and coding, analysis of marketing data, speech recognition, natural language understanding, and many more. Several other books cover aspects of this growing area; examples include Pearl (1988); Lauritzen (1996); Jensen (1996); Castillo et al. (1997a); Jordan (1998); Cowell et al. (1999); Neapolitan (2003); Korb and Nicholson (2003). The Artificial Intelligence textbook of Russell and Norvig (2003) places this field within the broader endeavor of constructing an intelligent agent.